How do I get an API key for Anytype MCP Server?
Open Anytype, go to App Settings, navigate to the API Keys section, and click “Create new.” Alternatively, run `npx -y @anyproto/anytype-mcp get-key` from your terminal.
@anyproto
基本情報
An MCP server enabling AI assistants to interact with Anytype - your encrypted, local and collaborative wiki - to organize objects, lists, and more through natural language.
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"anytype-mcp": {
"command": "npx",
"args": [
"-y",
"@anyproto/anytype-mcp",
"get-key"
]
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。
The Anytype MCP Server is a Model Context Protocol server that enables AI assistants to interact with Anytype's API through natural language. It converts Anytype’s OpenAPI specification into MCP tools, allowing users to manage their knowledge base conversationally.
First, obtain an API key from Anytype app settings or via the command npx -y @anyproto/anytype-mcp get-key. Then configure your MCP client by setting the OPENAPI_MCP_HEADERS environment variable with your key and the required Anytype-Version header. For custom API base URLs, set ANYTYPE_API_BASE_URL. Alternatively, install the package globally with npm install -g @anyproto/anytype-mcp.
Open Anytype, go to App Settings, navigate to the API Keys section, and click “Create new.” Alternatively, run `npx -y @anyproto/anytype-mcp get-key` from your terminal.
Claude Desktop, Cursor, Windsurf, Raycast, Claude Code (CLI), and any MCP client that accepts a JSON configuration.
Yes. Set the `ANYTYPE_API_BASE_URL` environment variable (default is `http://127.0.0.1:31009`). For example, `http://localhost:31012` works with `anytype-cli`.
Run `npm install -g @anyproto/anytype-mcp`, then use `anytype-mcp` as the command in your MCP client configuration.
You must provide `OPENAPI_MCP_HEADERS` with valid JSON containing `Authorization` (Bearer + your API key) and `Anytype-Version` (e.g., `"2025-11-08"`). `ANYTYPE_API_BASE_URL` is optional.
Local MCP server and CLI that keeps a Git-versioned, model-written index of a codebase and its database schema, so coding agents start each task with the whole system in view.
Shared, serverless, conflict-free memory for AI agents: a multi-machine drop-in for the MCP memory knowledge graph.

Shared memory for AI coding agents. Claude Code, Cursor and Codex read your project's decisions, lessons and tasks before they act.

Persistent memory for AI agents. Hosted MCP server with capsule-scoped key/value storage, tags, TTL expiration, bulk ops, and RBAC.

Local-first MCP server that snapshots your project's working state into one context object. Open-core, privacy-first.
コメント